ML Anthology

Salient Object Detection on Large-Scale Video Data

Shile Zhang, Jianping Fan, Hong Lu, Xiangyang Xue
CVPR 2007
doi:10.1109/CVPR.2007.383495 /cvpr/2007/zhang2007cvpr-salient/

Abstract

Recently more and more researches focus on the concept extraction from unstructured video data. To bridge the semantic gap between the low-level features and the high-level video concepts, a mid-level understanding of the video contents, i.e., salient object is detected based on the techniques of image segmentation and machine learning. Specifically, 21 salient object detectors are developed and tested on TRECVID 2005 development video corpus. In addition, a boosting method is proposed to select the most representative features to achieve a higher performance than only using single modality, and lower complexity than taking all features into account.

CVPR Semantic Scholar

Cite

Text

Zhang et al. "Salient Object Detection on Large-Scale Video Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383495

Markdown

[Zhang et al. "Salient Object Detection on Large-Scale Video Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/zhang2007cvpr-salient/) doi:10.1109/CVPR.2007.383495

BibTeX

@inproceedings{zhang2007cvpr-salient,
  title     = {{Salient Object Detection on Large-Scale Video Data}},
  author    = {Zhang, Shile and Fan, Jianping and Lu, Hong and Xue, Xiangyang},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383495},
  url       = {https://mlanthology.org/cvpr/2007/zhang2007cvpr-salient/}
}